Log inSubmit server
Agentlens logo

Agentlens

by agentkitai

Records AI agent activity in a SHA-256 hash chain and supports verification, signed export, and OpenTelemetry ingestion.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Agentlens

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "agentkitai-agentlens": {
      "command": "npx",
      "args": [
        "-y",
        "@agentkitai/agentlens-server"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

We couldn’t confirm it starts correctly

The install command didn't complete successfully in our automated test.

npx -y @agentkitai/agentlens-server

npm notice npm notice New major version of npm available! 10.1.0 -> 12.0.2 npm notice Changelog: <https://github.com/npm/cli/releases/tag/v12.0.2> npm notice Run `npm install -g npm@12.0.2` to update! npm notice npm ERR! could not determine executable to run npm ERR! A complete log of this run can be found in: /home/user/.npm/_logs/2026-09-22T11_25_23_272Z-debug-0.log

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 1mo ago.

Overview

The agentkitai/agentlens MCP server connects MCP clients such as Claude Desktop and Cursor to AgentLens for recording tool calls, sessions, and agent events. AgentLens stores events in an append-only audit log, linking each record with a SHA-256 hash so the chain can be verified after collection. The broader platform also accepts OpenTelemetry GenAI traces and provides a queryable API and web dashboard. Reach for it when an MCP-based agent needs tamper-evident activity records or audit-oriented observability.

Use cases

  • Record MCP tool calls for audit review
  • Verify that agent event history was not altered
  • Inspect MCP sessions in an observability dashboard
  • Ingest OpenTelemetry GenAI traces alongside MCP activity

Key features

  • SHA-256 hash-chained audit events
  • Audit-chain verification
  • Signed JSON audit export
  • MCP client integration
  • OpenTelemetry GenAI trace ingestion
  • SQLite or Postgres storage

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 3d ago

Recent health check succeeded.

19/19 checks healthy over the last 79d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 10d ago via OSV.dev · @agentkitai/agentlens-server (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars24Stargazers on the source repository.
npm downloads61Package downloads in the last 30 days.
Last commit10d agoMost recent push to the default branch.
Install checkInconclusiveInstall command did not finish in our automated test.
Directory activity5 viewsConfig copies, upvotes, and views on AllMCPs.

How Agentlens works

What agentkitai/agentlens MCP server does

The agentkitai/agentlens MCP server is the MCP-facing component of AgentLens, an observability system for AI agents. It connects MCP clients, including Claude Desktop and Cursor, to an AgentLens instance over HTTP. The integration records MCP tool calls, sessions, and related events for later inspection through the AgentLens API and dashboard.

AgentLens is designed around an append-only audit trail. Each event is linked to the preceding event with a SHA-256 hash. Verification can identify when a record has been altered, removed, or reordered. The server also supports the broader AgentLens workflow for preserving an audit record and producing a signed JSON export through the platform's verification export endpoint.

How it works

An MCP client sends activity through the AgentLens MCP integration. The MCP component forwards that activity to the AgentLens server, where the ingest and query components process it and store it in SQLite or Postgres. A dashboard is available from the server for viewing collected activity.

The platform can also ingest OpenTelemetry traces that use GenAI semantic conventions. OTLP HTTP traces sent to the AgentLens endpoints are mapped into events such as language-model calls, responses, tool calls, embeddings, and agent invocations. Traces become sessions, or use gen_ai.conversation.id when that identifier is present. These events receive the same hash-chain treatment as MCP-originated records.

Setup and configuration

The agentkitai/agentlens MCP server is distributed as an npm package named @agentkitai/agentlens-mcp. The repository also documents a separate AgentLens server package, @agentkitai/agentlens-server, which provides the receiving service and dashboard. A local AgentLens instance can run with SQLite and zero configuration through Docker or the server package.

For a quick local deployment, the documented Docker command publishes port 3400. Production-style deployments can use the repository's Docker Compose configuration with Postgres, Redis, authentication, and TLS settings.

Tools and capabilities

The agentkitai/agentlens MCP server supports:

  • Recording MCP tool calls, sessions, and agent events.
  • Sending MCP activity to an AgentLens HTTP service.
  • Preserving events in a SHA-256 hash-chained audit log.
  • Verifying whether the recorded chain remains intact.
  • Working alongside OpenTelemetry GenAI trace ingestion.
  • Inspecting collected activity through the AgentLens API and web dashboard.

AgentLens can reconstruct model-call cost from model identifiers and token usage for supported OpenTelemetry GenAI traces. Its documented integrations also include Python auto-instrumentation, an OpenClaw plugin, and SDKs, but those are separate from the MCP package.

Limitations and notes

The MCP package is only one part of the deployment: it needs an AgentLens server to receive and store the activity. The material does not list the individual MCP tool names or provide a standalone storage mode for the MCP package.

The quick local Docker example disables authentication and uses a development JWT secret, so it is intended for local trials. Shared or production deployments should use authentication and a real JWT secret. OpenTelemetry authentication can be enabled for OTLP endpoints with OTLP_AUTH_TOKEN.

The agentkitai/agentlens MCP server is open source under the MIT license. The repository describes its audit trail as suitable for EU AI Act Article 12 record-keeping, but compliance decisions still depend on the complete deployment and operating process.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Agentlens

Run `npx -y @agentkitai/agentlens-mcp`; the MCP package also requires an AgentLens server to receive and store events.

Yes. The repository lists Claude Desktop as an MCP client supported by the integration.

Yes. Cursor is listed as an MCP client that can send activity through the AgentLens MCP integration.

It links events with SHA-256 hashes in an append-only chain and reports verification failure when records are altered, deleted, or reordered.

Related MCP servers

All in Monitoring All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewAgentlens AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/agentkitai-agentlens?style=directory)](https://allmcps.com/mcp/agentkitai-agentlens)
HTML Embed
<a href="https://allmcps.com/mcp/agentkitai-agentlens"><img src="https://allmcps.com/api/badge/agentkitai-agentlens?style=directory" alt="Agentlens on AllMCPs" /></a>